Research on syntactic parsing with multiword expressions

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K16053
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Intelligent informatics
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Shindo Hiroyuki 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (20734784)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 構文解析 / 複合表現 / 複単語表現 / アノテーション

Outline of Final Research Achievements

In natural language processing, there is a lot of research on syntactic parsing exploiting word-based compositionality, that is, a meaning of phrase or sentence can be computed from the meaning of the words and the way they are combined. On the other hand, non-compositional expressions such as idiomatic constructions has been overlooked until now. In this work, we developed a method for syntactic parsing with identifying multiword expressions, and an efficient way to annotate multiword expressions on syntax trees. Further, we show that joint learning of syntactic parsing and identification of multiword expressions improves the performance of both tasks.

Free Research Field

自然言語処理